txt2vid error on Apple Silicon Mac

[volotat]

txt2vid error on Apple Silicon Mac

[Dcnigma]

look for this File "/stable-diffusion-webui/extensions/sd-cn-animation/scripts/core/txt2vid.py",
@ line 51,in **FloweR_load_model FloweR_model.load_state_dict(torch.load(model_path))**change that to > FloweR_model.load_state_dict(torch.load(model_path, map_location="cpu"))

That fixed it for me, but still waiting only at frame 4 of the 40 :-D

[kevinhower]

I get the same thing. Also on M1

[minorbug]

same here. welsh runs with the cpu/skip coda flags mentioned, so can the plugin do the same?

[Bloxmine]

look for this File "/stable-diffusion-webui/extensions/sd-cn-animation/scripts/core/txt2vid.py", @ line 51,in **FloweR_load_model FloweR_model.load_state_dict(torch.load(model_path))**change that to > FloweR_model.load_state_dict(torch.load(model_path, map_location="cpu"))

That fixed it for me, but still waiting only at frame 4 of the 40 :-D

This does work, although using the CPU to render isn't really as much a fix as it is a workaround.

[mrcaipeng]

In vid2vid mode, the same issue could happened. but I tried to fixe it by change the code in flow_utils.py.

At 55 line in flow_utils.py

change "RAFT_model.load_state_dict(torch.load(args.model))" to "RAFT_model.load_state_dict(torch.load(args.model, map_location=device))".

it works, but the performance is very bad.

[murtuk]

I get the same error on M2 too. I make changes mentioned above one by one and together - but I still get only one frame and this error when I make the changes: "An exception occurred while trying to process the frame: Input type (MPSFloatType) and weight type (torch.FloatTensor) should be the same"